Minor question template & score_answer improvements (#261)

* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
This commit is contained in:
Andreas Köpf 2025-03-04 21:55:09 +01:00 committed by GitHub
parent bf24999bb0
commit b2904ccab9
106 changed files with 403 additions and 507 deletions

View file

@ -108,9 +108,9 @@ class BinaryMatrixDataset(ProceduralDataset):
# check if answer is python list of lists
answer = self._matrix_to_str(eval(answer))
if answer == oracle_answer:
return 0.5
except Exception as e:
return 0.01
return 0.1
except Exception:
return 0.0
return 0.0
def __getitem__(self, idx: int) -> dict: